EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Camera traps and deep learning enable efficient large‐scale density estimation of wildlife in temperate forest ecosystems

Maik Henrich, Christian Fiderer, Alisa Klamm, Anja Schneider, Axel Ballmann, Jürgen Stein, Raffael Kratzer, Rudolf Reiner, Sina Greiner, Sönke Twietmeyer, Tobias Rönitz, Volker Spicher und 4 weitere

Remote Sensing in Ecology and Conservation · 2026-02 · 12 (1) · 148-163

DOI: 10.1002/rse2.70030 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing in Ecology and Conservation, online erschienen am 08.09.2025. Verfasst von Maik Henrich und 15 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Biodiversa+, Bundesministerium für Bildung und Forschung, Bundesamt für Naturschutz.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automated detectors such as camera traps allow the efficient collection of large amounts of data for the monitoring of animal populations, but data processing and classification are a major bottleneck. Deep learning algorithms have gained increasing attention in this context, as they have the potential to dramatically decrease the time and effort required to obtain population density estimates. However, the robustness of such an approach has not yet been evaluated across a wide range of species and study areas. This study evaluated the application of DeepFaune, an open‐source deep learning algorithm for the classification of European animal species and camera trap distance sampling (CTDS) to a year‐round dataset containing 895,019 manually classified photos from 10 protected areas across Germany. For all wild animal species and higher taxonomic groups on which DeepFaune was trained, the algorithm achieved an overall accuracy of 90%. The 95% confidence interval (CI) of the difference between the CTDS estimates based on manual and automated image classification contained zero for all species and seasons with a minimum sample size of 20 independent observations per study area, except for two. Meta‐regression revealed an average difference between the classification methods of −0.005 (95% CI: −0.205–0.196) animals/km 2 . Classification success correlated with the divergence of the population density estimates, but false negative and false positive detections had complex effects on the density estimates via different CTDS parameters. Therefore, metrics of classification performance alone are insufficient to assess the effect of deep learning classifiers on the population density estimation process, which should instead be followed through entirely for proper validation. In general, however, our results demonstrate that readily available deep learning algorithms can be used in largely unsupervised workflows for estimating population densities from camera trap data.

Förderung

  • Biodiversa+
  • Bundesministerium für Bildung und Forschung
  • Bundesamt für Naturschutz
  • Bayerisches Staatsministerium für Umwelt und Verbraucherschutz

Zitieren

APA

Henrich, M., Fiderer, C., Klamm, A., Schneider, A., Ballmann, A., Stein, J., Kratzer, R., Reiner, R., Greiner, S., Twietmeyer, S., Rönitz, T., Spicher, V., Chamaillé‐Jammes, S., Miele, V., Dussert, G., & Heurich, M. (2026). Camera traps and deep learning enable efficient large‐scale density estimation of wildlife in temperate forest ecosystems. Remote Sensing in Ecology and Conservation, 12(1), 148-163. https://doi.org/10.1002/rse2.70030

Vancouver

Henrich M, Fiderer C, Klamm A, Schneider A, Ballmann A, Stein J, et al. Camera traps and deep learning enable efficient large‐scale density estimation of wildlife in temperate forest ecosystems. Remote Sensing in Ecology and Conservation. 2026;12(1):148-163. doi:10.1002/rse2.70030

BibTeX
@article{Henrich2026,
  author = {Henrich, Maik and Fiderer, Christian and Klamm, Alisa and Schneider, Anja and Ballmann, Axel and Stein, Jürgen and Kratzer, Raffael and Reiner, Rudolf and Greiner, Sina and Twietmeyer, Sönke and Rönitz, Tobias and Spicher, Volker and Chamaillé‐Jammes, Simon and Miele, Vincent and Dussert, Gaspard and Heurich, Marco},
  title = {Camera traps and deep learning enable efficient large‐scale density estimation of wildlife in temperate forest ecosystems},
  journal = {Remote Sensing in Ecology and Conservation},
  year = {2026},
  volume = {12},
  number = {1},
  pages = {148--163},
  doi = {10.1002/rse2.70030}
}
Kostenlos starten →